Grok 4.5 Uses Significantly Fewer Tokens
XFreeze · x · 2026-07-09
According to a post, Grok 4.5 consumes far fewer output tokens on SWE Bench Pro compared to Claude Opus 4.8 max. It averages 15,954 output tokens versus 67,020 for the latter, roughly a 4.2x reduction. The author also reported a response throughput of 80 TPS, emphasizing lower inference costs, faster responses, and better scalability.
Related event: xAI Launches Grok 4.5: Coding and Agent Focus to Rival Opus(55 posts)→
More from Infra
- Sail equivalence proof and riscv-coq cross-checks uncover real RISC-V spec bugs — xennygrimmato_ · 2026-10-27
- xAI's Colossus 1 hits ~14.6 exaflops FP64, ~5x Top500 leader — cis_female · 2026-10-27
- Lambda runs 19 B200 nodes in a 16-node power budget, boosting throughput 24% — TheZachMueller · 2026-10-27
- Podcast: Micron's HBM roadmap, Meta's AI infra, and NVIDIA's supply chain lock-in — BenBajarin · 2026-10-27
- SGLang MegaKernel + PD Pushes the TCO-Latency Frontier on GB300, SemiAnalysis Benchmarks Show — AccBalanced · 2026-10-27
- Scaling self-hosted Convex: compiling TypeScript Convex functions to WASM — leventov · 2026-10-27